© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25935
    Prev
    Next
    INDEX
    Explanations

    urls involving cdn or paths

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects tokens that are parts of URLs or hostname components (e.g. CDN or domain name segments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     卧室
    -0.94
     invitaciones
    -0.93
     recomendada
    -0.93
     vehicles
    -0.92
    ⚋
    -0.88
    ACTS
    -0.85
     patrones
    -0.84
     hoteles
    -0.84
     bonos
    -0.84
     administrativo
    -0.84
    POSITIVE LOGITS
    ̃
    0.82
     получи
    0.79
     restarting
    0.77
    きます
    0.76
    $
    0.76
     он
    0.73
    økt
    0.71
     практически
    0.71
     Beit
    0.70
     именно
    0.70
    Activations Density 0.004%

    No Known Activations